Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ≥

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    okrat
    -0.07
    ylland
    -0.07
    istrator
    -0.06
    rawer
    -0.06
     먼저
    -0.06
     sober
    -0.06
     Ones
    -0.06
    _normalize
    -0.06
    чного
    -0.06
    ันน
    -0.06
    POSITIVE LOGITS
     ≥
    0.09
    ≥
    0.07
     QUEUE
    0.07
     protest
    0.07
     เ
    0.07
    ≤
    0.07
     uLocal
    0.07
     facilitating
    0.07
     ≤
    0.06
     equipos
    0.06
    Act Density 0.002%

    No Known Activations